Computing Life · An engineering notebook
Long-form notes on agentic systems, engineering judgment, astrophotography, hardware, coffee, and the tools that make a life easier to inspect and improve.
Technical lessons from building an AI video transcription tool: YouTube OAuth2 authentication, async task-based APIs, Python concurrency patterns, GPT laziness issues, and iOS Shortcuts integration.
反思为何正确性不是思考的核心目标，提出真正重要的是纲举目张（Prioritization）、举一反三（Connection）和知行合一（Verification）三种能力。
视频信息密度低、不可检索、难以跳转，但up主赚大钱而写文章不赚钱。核心在于视频让"作者"站到前台，观众更容易产生情感连接和付费意愿。
Videos are terrible for learning—can't skim, search, or navigate easily. Yet creators make millions because video makes the "author" tangible, lowering the barrier to payment. Articles hide the author behind ideas.
提出AI辅助编程的核心从数据结构和算法转向注释和DocString的质量。类比管理AI与管理人类团队，强调了解能力边界、任务分解、委托和质量检查等开发经理式的思维方式。
Argues that effective AI-assisted programming shifts focus from data structures and algorithms to writing detailed comments and DocStrings. Draws parallels between managing AI and managing human teams, emphasizing delegation, context provision, and quality checks.
对比三种写课程介绍的策略：完全AI、AI辅助、完全人肉。发现人类写作自然流露的张力与感染力是AI外交式疏离风格所缺乏的，选择不用AI本身也是对用户的尊重。
Compares three approaches to writing a course introduction—fully AI, AI-assisted, and fully human. Reveals that human writing conveys tension and engagement that AI's diplomatic, detached style lacks, and choosing not to use AI can itself show respect to users.
Prompt Engineering实战指南：匹配任务与AI能力、上下文窗口管理、知识查询可靠性提升、数学计算与机器人控制等场景下利用Agent增强能力的方法。
A practical guide to prompt engineering: matching tasks to LLM capabilities, managing context windows, using web search for reliability, and leveraging agents for domains like math and robotics.